Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add ztemerbekov/a1-marketing-skills --skill a1-presentation-copygit clone --depth 1 https://github.com/ztemerbekov/a1-marketing-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/ztemerbekov/a1-marketing-skills/a1-presentation-copy)<a href="https://agentmods.dev/skills/ztemerbekov/a1-marketing-skills/a1-presentation-copy"><img src="https://agentmods.dev/badge/skills/ztemerbekov/a1-marketing-skills/a1-presentation-copy/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ztemerbekov/a1-marketing-skills/a1-presentation-copy"><img src="https://agentmods.dev/badge/skills/ztemerbekov/a1-marketing-skills/a1-presentation-copy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00049 | $0.00490 |
| Opus 5 | $0.00024 | $0.00245 |
| Sonnet 5 | $0.00010 | $0.00098 |
| Haiku 4.5 | $0.00005 | $0.00049 |
Grade A, and why
a1-presentation-copy scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Presentation Copy
Turn source material into a presentation whose slides each carry one useful point for a specific audience and occasion.
Entry Contract
Accept a request when every requested deliverable contributes to one new presentation. Select Outline for message architecture, slide sequence, or an evidence plan. Select Draft for slide-by-slide copy. Supplied research, data, strategy, speaker notes, product material, and visual assets are completed inputs this skill may consume.
This skill creates presentation content, not a .pptx or Google Slides file. It does not conduct missing research, invent strategy, calculate unsupported data, design layouts, or edit a selected existing deck.
For a mixed request, state the boundary and stop before producing presentation content.
Marketing Context is optional. Read only the first existing repository context in this order: .agents/marketing-context.md, then .claude/marketing-context.md when the canonical path is absent, then root marketing-context.md when both earlier paths are absent. Read no lower-priority context after selecting one. Continue without context when none exists.
Runtime
Follow the presentation-copy spine for every accepted request. Apply the source policy before choosing the narrative path or slide claims.
Output
For Outline, return the presentation job and an ordered slide sequence. For each slide, give the takeaway, evidence or visual required, and its role in the audience's path.
For Draft, return slide-by-slide copy with a takeaway headline, essential on-slide content, and an evidence-bearing visual instruction when useful. Include speaker notes only when requested.
If the user requests only the outline, only the slide copy, or only the final artifact, return exactly that artifact.
Append exactly one support footer inviting questions, ideas, or problem reports via A1 Marketing Skills only after a final user-facing result that fulfills this skill's job. Omit it for boundary responses, clarification prompts, unsuccessful results, or artifact-only requests.
What ships with it
10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 385 B
- assets/icon-large.svg 2.3 KB
- assets/icon-small.svg 2.3 KB
- evals/cases/presentation-existing-deck-004.md 840 B
- evals/cases/presentation-live-draft-002.md 1.2 KB
- evals/cases/presentation-outline-001.md 1.3 KB
- evals/cases/presentation-unsupported-data-003.md 1.1 KB
- evals/README.md 563 B
- references/presentation-copy-spine.md 2.6 KB
- references/source-policy.md 861 B
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 35 lines · 49 tokens per session scan A a49c41fb361b
a1-presentation-copy is a skill published in the GitHub repository ztemerbekov/a1-marketing-skills (8 stars, last pushed 13d ago), licensed MIT. It adds 49 tokens to every session and 490 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
deai_humanize
A Chinese-language writing helper that measures signs of machine-like writing and rewrites text to sound more natural and personal.
humanize-automation
Human-like mouse, keyboard and scroll behavior for behavioral bot bypass.
analytics-strategy
Design measurement frameworks including event taxonomy, KPI hierarchy, dashboard architecture, attribution models, and analytics implementation strategy. Use this skill whenever the user wants to plan analytics, design dashboards, build event taxonomies, define KPIs, set up tracking, or audit existing measurement.…
cro-optimization
Run conversion rate optimization through hypothesis-driven testing including audit, hypothesis generation, test design, statistical analysis, and rollout decisions. Use this skill whenever the user wants to optimize conversion, run A/B tests, audit a funnel, generate test hypotheses, design experiments, or analyze…
research-seo-demand
A Chinese-language process for researching SEO opportunities, where SEO means improving pages so they can appear in search results. It studies user needs, keyword demand, search-result pages, and competing pages using Bing data.
create-seo-page
A Chinese-language workflow for creating and implementing search-focused pages in an existing product repository. SEO means improving a page so it can be found and understood through search engines.